From be13336e07b5cc26c8b971a50ff6dc60d7050417 Mon Sep 17 00:00:00 2001 From: Aravind Iddamsetty Date: Fri, 10 Nov 2023 15:41:56 +0000 Subject: [PATCH] drm/xe/pmu: Drop interrupt pmu event Drop interrupt event from PMU as that is not useful and not being used by any UMD. Cc: Rodrigo Vivi Cc: Tvrtko Ursulin Cc: Francois Dugast Signed-off-by: Aravind Iddamsetty Reviewed-by: Francois Dugast Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_irq.c | 18 ------------------ drivers/gpu/drm/xe/xe_pmu.c | 19 +++++-------------- drivers/gpu/drm/xe/xe_pmu_types.h | 8 -------- include/uapi/drm/xe_drm.h | 13 ++++++------- 4 files changed, 11 insertions(+), 47 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c index c5315e02fc5bb..25ba5167c1b92 100644 --- a/drivers/gpu/drm/xe/xe_irq.c +++ b/drivers/gpu/drm/xe/xe_irq.c @@ -27,20 +27,6 @@ #define IIR(offset) XE_REG(offset + 0x8) #define IER(offset) XE_REG(offset + 0xc) -/* - * Interrupt statistic for PMU. Increments the counter only if the - * interrupt originated from the GPU so interrupts from a device which - * shares the interrupt line are not accounted. - */ -static __always_inline void xe_pmu_irq_stats(struct xe_device *xe) -{ - /* - * A clever compiler translates that into INC. A not so clever one - * should at least prevent store tearing. - */ - WRITE_ONCE(xe->pmu.irq_count, xe->pmu.irq_count + 1); -} - static void assert_iir_is_zero(struct xe_gt *mmio, struct xe_reg reg) { u32 val = xe_mmio_read32(mmio, reg); @@ -360,8 +346,6 @@ static irqreturn_t xelp_irq_handler(int irq, void *arg) xe_display_irq_enable(xe, gu_misc_iir); - xe_pmu_irq_stats(xe); - return IRQ_HANDLED; } @@ -458,8 +442,6 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg) dg1_intr_enable(xe, false); xe_display_irq_enable(xe, gu_misc_iir); - xe_pmu_irq_stats(xe); - return IRQ_HANDLED; } diff --git a/drivers/gpu/drm/xe/xe_pmu.c b/drivers/gpu/drm/xe/xe_pmu.c index abfc0b3aeac41..b843259578fd2 100644 --- a/drivers/gpu/drm/xe/xe_pmu.c +++ b/drivers/gpu/drm/xe/xe_pmu.c @@ -61,7 +61,7 @@ static u64 __engine_group_busyness_read(struct xe_gt *gt, int sample_type) static u64 engine_group_busyness_read(struct xe_gt *gt, u64 config) { - int sample_type = config_counter(config) - 1; + int sample_type = config_counter(config); const unsigned int gt_id = gt->info.id; struct xe_device *xe = gt->tile->xe; struct xe_pmu *pmu = &xe->pmu; @@ -114,10 +114,6 @@ config_status(struct xe_device *xe, u64 config) return -ENOENT; switch (config_counter(config)) { - case XE_PMU_INTERRUPTS(0): - if (gt_id) - return -ENOENT; - break; case XE_PMU_RENDER_GROUP_BUSY(0): case XE_PMU_COPY_GROUP_BUSY(0): case XE_PMU_ANY_ENGINE_GROUP_BUSY(0): @@ -181,13 +177,9 @@ static u64 __xe_pmu_event_read(struct perf_event *event) const unsigned int gt_id = config_gt_id(event->attr.config); const u64 config = event->attr.config; struct xe_gt *gt = xe_device_get_gt(xe, gt_id); - struct xe_pmu *pmu = &xe->pmu; u64 val; switch (config_counter(config)) { - case XE_PMU_INTERRUPTS(0): - val = READ_ONCE(pmu->irq_count); - break; case XE_PMU_RENDER_GROUP_BUSY(0): case XE_PMU_COPY_GROUP_BUSY(0): case XE_PMU_ANY_ENGINE_GROUP_BUSY(0): @@ -361,11 +353,10 @@ create_event_attributes(struct xe_pmu *pmu) const char *unit; bool global; } events[] = { - __global_event(0, "interrupts", NULL), - __event(1, "render-group-busy", "ns"), - __event(2, "copy-group-busy", "ns"), - __event(3, "media-group-busy", "ns"), - __event(4, "any-engine-group-busy", "ns"), + __event(0, "render-group-busy", "ns"), + __event(1, "copy-group-busy", "ns"), + __event(2, "media-group-busy", "ns"), + __event(3, "any-engine-group-busy", "ns"), }; struct perf_pmu_events_attr *pmu_attr = NULL, *pmu_iter; diff --git a/drivers/gpu/drm/xe/xe_pmu_types.h b/drivers/gpu/drm/xe/xe_pmu_types.h index 4ccc7e9042f64..9cadbd243f577 100644 --- a/drivers/gpu/drm/xe/xe_pmu_types.h +++ b/drivers/gpu/drm/xe/xe_pmu_types.h @@ -51,14 +51,6 @@ struct xe_pmu { * */ u64 sample[XE_PMU_MAX_GT][__XE_NUM_PMU_SAMPLERS]; - /** - * @irq_count: Number of interrupts - * - * Intentionally unsigned long to avoid atomics or heuristics on 32bit. - * 4e9 interrupts are a lot and postprocessing can really deal with an - * occasional wraparound easily. It's 32bit after all. - */ - unsigned long irq_count; /** * @events_attr_group: Device events attribute group. */ diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 097d045d04445..e007dbefd6274 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -977,7 +977,7 @@ struct drm_xe_wait_user_fence { * in 'struct perf_event_attr' as part of perf_event_open syscall to read a * particular event. * - * For example to open the XE_PMU_INTERRUPTS(0): + * For example to open the XE_PMU_RENDER_GROUP_BUSY(0): * * .. code-block:: C * @@ -991,7 +991,7 @@ struct drm_xe_wait_user_fence { * attr.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED; * attr.use_clockid = 1; * attr.clockid = CLOCK_MONOTONIC; - * attr.config = XE_PMU_INTERRUPTS(0); + * attr.config = XE_PMU_RENDER_GROUP_BUSY(0); * * fd = syscall(__NR_perf_event_open, &attr, -1, cpu, -1, 0); */ @@ -1004,11 +1004,10 @@ struct drm_xe_wait_user_fence { #define ___XE_PMU_OTHER(gt, x) \ (((__u64)(x)) | ((__u64)(gt) << __XE_PMU_GT_SHIFT)) -#define XE_PMU_INTERRUPTS(gt) ___XE_PMU_OTHER(gt, 0) -#define XE_PMU_RENDER_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 1) -#define XE_PMU_COPY_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 2) -#define XE_PMU_MEDIA_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 3) -#define XE_PMU_ANY_ENGINE_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 4) +#define XE_PMU_RENDER_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 0) +#define XE_PMU_COPY_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 1) +#define XE_PMU_MEDIA_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 2) +#define XE_PMU_ANY_ENGINE_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 3) #if defined(__cplusplus) } -- 2.30.2